JoPmt/Trismal-HyperUnion-7B-Base-v1.5v3A-Ties

Full fine-tune vs Locutusque/Hyperion-1.5-Mistral-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 1/1

1 derivatives checked

• mradermacher/Trismal-HyperUnion-7B-Base-v1.5v3A-Ties-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse